arm64: perf: Implement correct cap_user_time

#include <linux/of.h>

#include <linux/perf/arm_pmu.h>

#include <linux/platform_device.h>

#include <linux/sched_clock.h>

#include <linux/smp.h>

/* ARMv8 Cortex-A53 specific event types. */

void arch_perf_update_userpage(struct perf_event *event,

			       struct perf_event_mmap_page *userpg, u64 now)

{

	u32 freq;

	u32 shift;

	struct clock_read_data *rd;

	unsigned int seq;

	u64 ns;

	/*

	 * Internal timekeeping for enabled/running/stopped times

	 * is always computed with the sched_clock.

	 */

	freq = arch_timer_get_rate();

	userpg->cap_user_time = 1;

	userpg->cap_user_time_zero = 1;

	do {

		rd = sched_clock_read_begin(&seq);

		userpg->time_mult = rd->mult;

		userpg->time_shift = rd->shift;

		userpg->time_zero = rd->epoch_ns;

		/*

		 * This isn't strictly correct, the ARM64 counter can be

		 * 'short' and then we get funnies when it wraps. The correct

		 * thing would be to extend the perf ABI with a cycle and mask

		 * value, but because wrapping on ARM64 is very rare in

		 * practise this 'works'.

		 */

		ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);

		userpg->time_zero -= ns;

	} while (sched_clock_read_retry(seq));

	userpg->time_offset = userpg->time_zero - now;

	clocks_calc_mult_shift(&userpg->time_mult, &shift, freq,

			NSEC_PER_SEC, 0);

	/*

	 * time_shift is not expected to be greater than 31 due to

	 * the original published conversion algorithm shifting a

	 * 32-bit value (now specifies a 64-bit value) - refer

	 * perf_event_mmap_page documentation in perf_event.h.

	 */

	if (shift == 32) {

		shift = 31;

	if (userpg->time_shift == 32) {

		userpg->time_shift = 31;

		userpg->time_mult >>= 1;

	}

	userpg->time_shift = (u16)shift;

	userpg->time_offset = -now;

}